Thursday, October 23, 2025 - A Kenyan entrepreneur who created a web-based app that translates speech into sign language using AI-powered 3D avatars has won a major award for African innovation.
Elly Savatia, creator of the app Terp 360, was awarded
£50,000 ($67,000) on October 16 by the UK’s Royal Academy of Engineering. He
won its prestigious Africa Prize for Engineering Innovation, which recognizes
technology developed to address challenges on the continent. Savatia's
innovation was selected from four finalists across Africa during a ceremony
held in Dakar, Senegal.
Savatia described his creation as "Google Translate for
sign language," explaining that it takes speech and text input and outputs
photorealistic avatars signing in real time, allowing users to communicate
without relying on human interpreters.
He noted that the deaf community in Kenya often struggles to
access essential services like education and health care because many
professionals do not know sign language. Human interpreters are expensive and
scarce, resulting in many deaf people across Africa failing to transition to
higher education.
While a government bill was passed earlier this year
requiring Kenyan employers to reserve at least 5% of jobs for people with
disabilities, Savatia explained that many roles remain inaccessible because
companies "cannot afford interpreters" or simply lack the tools to
effectively integrate deaf employees. Terp 360 aims to be an
"enabler" that can provide sign language translation at scale.
Terp 360 was developed in conjunction with deaf and
hard-of-hearing Kenyans to record over 2,300 signs, including commonly used
phrases and words. Motion sensors were attached to a signer's hands to capture
the movements for the AI training.
While other avatar-based sign language technologies exist
globally, Savatia emphasized that they are often not designed with African sign
languages or cultural context in mind. With more than 300 sign languages used
worldwide and about 30 in Africa, Terp 360 currently translates from English
and Swahili into Kenyan Sign Language.
Savatia stated that the app is on track to support Rwandan,
Ugandan, South African, British, and American sign languages by mid-2027, with
plans to translate from other major African and global languages.
To train the AI in new languages, the developers plan to
partner with local NGOs, projects that have visual sign language data sets, and
news stations with sign language video archives. They have also established a
motion capture studio in Nairobi with the capacity to record and learn 1,000
words a day.
Rebecca Enonchong, chair of the prize-judging panel,
highlighted the "cutting-edge technology" demonstrated by the
solution and its significant social impact, noting that assistive technologies
are an underserved area globally.
0 Comments